{"id":"https://openalex.org/W3003499901","doi":"https://doi.org/10.1109/tcds.2020.2970487","title":"A Multitier Reinforcement Learning Model for a Cooperative Multiagent System","display_name":"A Multitier Reinforcement Learning Model for a Cooperative Multiagent System","publication_year":2020,"publication_date":"2020-01-30","ids":{"openalex":"https://openalex.org/W3003499901","doi":"https://doi.org/10.1109/tcds.2020.2970487","mag":"3003499901"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2020.2970487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.2970487","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013665827","display_name":"Haobin Shi","orcid":"https://orcid.org/0000-0003-2180-8941"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Shi","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0003-2180-8941","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084150509","display_name":"Liangjing Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangjing Zhai","raw_affiliation_strings":["School of Software and Microelectronics, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049705446","display_name":"Haibo Wu","orcid":"https://orcid.org/0000-0003-4347-9472"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Wu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066851929","display_name":"Maxwell Hwang","orcid":"https://orcid.org/0000-0002-9505-6263"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maxwell Hwang","raw_affiliation_strings":["School of Medicine, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Medicine, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaoshiung, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9234-4836","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Kaoshiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058795369","display_name":"Hsuan-Pei Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsuan-Pei Hsu","raw_affiliation_strings":["HonestBee, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HonestBee, Taipei, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8213,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.88134532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"12","issue":"3","first_page":"636","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.891610324382782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8054962158203125},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.6240823268890381},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5795391201972961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5189887881278992},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5042070150375366},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49189281463623047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32448557019233704},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.11611300706863403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08472079038619995}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.891610324382782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8054962158203125},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.6240823268890381},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5795391201972961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189887881278992},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5042070150375366},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49189281463623047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32448557019233704},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.11611300706863403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08472079038619995},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2020.2970487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.2970487","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G2194264901","display_name":null,"funder_award_id":"61976178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W169931978","https://openalex.org/W568318363","https://openalex.org/W1526203454","https://openalex.org/W1975978837","https://openalex.org/W1980737627","https://openalex.org/W1981289969","https://openalex.org/W2038416433","https://openalex.org/W2103076989","https://openalex.org/W2107544712","https://openalex.org/W2108267069","https://openalex.org/W2124716489","https://openalex.org/W2155220448","https://openalex.org/W2164913115","https://openalex.org/W2491537827","https://openalex.org/W2561001448","https://openalex.org/W2586106701","https://openalex.org/W2730328371","https://openalex.org/W2761465998","https://openalex.org/W2783134749","https://openalex.org/W2789901741","https://openalex.org/W2963937357","https://openalex.org/W3143250040","https://openalex.org/W4233776596","https://openalex.org/W4242450948","https://openalex.org/W4297789683","https://openalex.org/W6644281795","https://openalex.org/W6659933788","https://openalex.org/W6678424871","https://openalex.org/W6743367460"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W2154793587","https://openalex.org/W4319083788","https://openalex.org/W2073900753","https://openalex.org/W1966682685","https://openalex.org/W4206669594","https://openalex.org/W2169203366","https://openalex.org/W77396219","https://openalex.org/W1972847450","https://openalex.org/W2386664274"],"abstract_inverted_index":{"In":[0],"multiagent":[1],"cooperative":[2,56,61,80,135],"systems":[3,57],"with":[4],"value-based":[5],"reinforcement":[6,92],"learning,":[7],"agents":[8,41,54,88],"learn":[9],"how":[10,25],"to":[11,26,36],"complete":[12],"the":[13,50,60,65,79,84,102,107,110,113,119,141,146,166],"task":[14],"by":[15,58,68,82],"an":[16,43],"optimal":[17,114],"policy":[18,29,70,104,156],"learned":[19],"through":[20,101,118],"value-policy":[21],"improvement":[22],"iterations.":[23],"But":[24],"design":[27],"a":[28,37,90,151],"that":[30,48,140],"avoids":[31],"cooperation":[32,85],"dilemmas":[33],"and":[34,63,148,159,171],"comes":[35],"common":[38],"consensus":[39],"between":[40],"is":[42,71,116,131,168],"important":[44],"issue.":[45],"A":[46],"method":[47,77,130],"improves":[49],"coordination":[51],"ability":[52],"of":[53,109],"in":[55,73,89,150],"assessing":[59],"tendency":[62],"increases":[64],"collective":[66],"payoff":[67,108],"candidate":[69,96,103,126],"proposed":[72,142],"this":[74],"article.":[75],"The":[76,95,129,137],"learns":[78],"rules":[81],"recording":[83],"probabilities":[86],"for":[87],"multitier":[91],"learning":[93,154],"model.":[94],"action":[97,127],"sets":[98],"are":[99],"selected":[100,117],"which":[105,144],"considers":[106],"coalition.":[111],"Then,":[112],"strategy":[115],"Nash":[120],"bargaining":[121],"solution":[122],"(NBS)":[123],"from":[124],"these":[125],"sets.":[128],"tested":[132],"using":[133],"two":[134],"tasks.":[136],"results":[138],"show":[139],"algorithm,":[143],"addresses":[145],"instability":[147],"ambiguity":[149],"win":[152],"or":[153],"fast":[155],"hill-climbing":[157],"(WoLF-PHC)":[158],"requires":[160],"significantly":[161],"less":[162],"memory":[163],"space":[164],"than":[165,174],"NBS,":[167],"more":[169,172],"stable":[170],"efficient":[173],"other":[175],"methods.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
